{"total":30,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2510.11701","title":"Demystifying Reinforcement Learning in Agentic Reasoning","created":"2025-10-13","cited_by_count":33,"area":"lr"},{"id":"2509.21474","title":"d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation","created":"2025-09-25","cited_by_count":27,"area":"lr"},{"id":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2510.02212","title":"DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2512.09675","title":"d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models","created":"2025-12-10","cited_by_count":17,"area":"lr"},{"id":"2512.04459","title":"dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning","created":"2025-12-04","cited_by_count":14,"area":"lr"},{"id":"2510.01544","title":"Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2603.06743","title":"Stabilizing Reinforcement Learning for Diffusion Language Models","created":"2026-03-06","cited_by_count":10,"area":"lr"},{"id":"2603.22458","title":"MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2509.25604","title":"RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2602.14147","title":"LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models","created":"2026-02-15","cited_by_count":7,"area":"lr"},{"id":"2603.13319","title":"LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning","created":"2026-03-04","cited_by_count":6,"area":"lr"},{"id":"2606.19257","title":"DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models","created":"2026-06-17","cited_by_count":5,"area":"lr"},{"id":"2510.09544","title":"Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2606.08501","title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","created":"2026-06-07","cited_by_count":4,"area":"lr"},{"id":"2511.15208","title":"Reasoning in Diffusion Large Language Models is Concentrated in Dynamic Confusion Zones","created":"2025-11-19","cited_by_count":3,"area":"lr"},{"id":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2603.01563","title":"LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2607.15200","title":"Mask-Aware Policy Gradients for Diffusion Language Models","created":"2026-07-16","cited_by_count":3,"area":"lr"},{"id":"2602.09555","title":"Adaptive Test-Time Compute Allocation for Block Diffusion Language Models in Complex Reasoning","created":"2026-02-10","cited_by_count":2,"area":"lr"},{"id":"2604.16565","title":"Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models","created":"2026-04-17","cited_by_count":2,"area":"lr"},{"id":"2605.02263","title":"Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2605.10218","title":"Relative Score Policy Optimization for Diffusion Language Models","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2606.23567","title":"Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models","created":"2026-06-22","cited_by_count":1,"area":"lr"},{"id":"2601.17426","title":"A Syllogistic Probe: Tracing the Evolution of Logic Reasoning in Large Language Models","created":"2026-01-24","cited_by_count":0,"area":"lr"},{"id":"2607.01170","title":"Diffusion-GR2: Diffusion Generative Reasoning Re-ranker","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2610.00661","title":"Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.03326","title":"Preserving Mathematical Reasoning in Compressed Diffusion Language Models via Trajectory-Aware Low-Rank Approximation","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}